Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    cassert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Actual
    -0.07
     shirts
    -0.07
    عر
    -0.07
    getting
    -0.07
     COP
    -0.07
    ))
    -0.07
    ASF
    -0.07
    Save
    -0.07
     grow
    -0.06
     shade
    -0.06
    POSITIVE LOGITS
     yayınlan
    0.07
     Nome
    0.06
    殣
    0.06
     lah
    0.06
    华南
    0.06
     crem
    0.06
    .APPLICATION
    0.06
     démarch
    0.06
    人民群众
    0.06
     ensued
    0.06
    Act Density 0.001%

    No Known Activations